mlsanityData to 14 Oct 2026

Data Augmentation in Training CNNs: Injecting Noise to Images

arXiv 2307.06855 ↗First posted 12 Jul 2023cs.CV cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Noise injection is a fundamental tool for data augmentation, and yet there is no widely accepted procedure to incorporate it with learning frameworks. This study analyzes the effects of adding or applying different noise models of varying magnitudes to Convolutional Neural Network (CNN) architectures. Noise models that are distributed with different density functions are given common magnitude levels via Structural Similarity (SSIM) metric in order to create an appropriate ground for comparison. The basic results are conforming with the most of the common notions in machine learning, and also introduce some novel heuristics and recommendations on noise injection. The new approaches will provide better understanding on optimal learning procedures for image classification.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 5 of its 22 references that are in the map. First posted on arXiv 12 Jul 2023.

Builds on

5 of 22 references.

References · 5

  1. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  2. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  3. 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
  4. 2016A Curriculum Learning Method for Improved Noise Robustness in Automatic Speech Recognitioncited by 23
  5. 2017TumorNet: Lung Nodule Characterization Using Multi-View Convolutional Neural Network with Gaussian Processcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 4; 2026: 1.

10 papers.

  1. 2025PatchGuard: Adversarially Robust Anomaly Detection and Localization through Vision Transformers and Pseudo Anomaliescited by 8
  2. 2023SymNoise: Advancing Language Model Fine-tuning with Symmetric Noisecited by 4
  3. 2025FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speedcited by 3
  4. 2024Policy Gradient-Driven Noise Maskcited by 2
  5. 2023The Benefit of Noise-Injection for Dynamic Gray-Box Model Creationcited by 0
  6. 2024Mean Teacher based SSL Framework for Indoor Localization Using Wi-Fi RSSI Fingerprintingcited by 0
  7. 2024Harnessing the Power of Noise: A Survey of Techniques and Applicationscited by 0
  8. 2025Using machine learning to map simulated noisy and laser-limited multidimensional spectra to molecular electronic couplingscited by 0
  9. 2025Noise Injection: Improving Out-of-Distribution Generalization for Limited Size Datasetscited by 0
  10. 2026Understanding and Improving Noisy Embedding Techniques in Instruction Finetuningcited by 0